© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68070
    Prev
    Next
    INDEX
    Explanations

    finding file paths

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on filesystem path– and file‐manipulation tokens (e.g. file names, directory globs, join/Dir calls, find/path patterns).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     with
    -1.18
     when
    -1.09
     as
    -1.09
     cometer
    -1.06
    masyarakat
    -1.05
     samband
    -1.05
    giày
    -1.04
     information
    -1.03
    casco
    -1.02
     used
    -1.01
    POSITIVE LOGITS
     principalmente
    1.30
     кроме
    1.18
    discovered
    1.16
    崭
    1.16
    excluding
    1.16
    except
    1.13
    mainly
    1.13
     Eſ
    1.11
    primarily
    1.10
     wyłą
    1.09
    Activations Density 0.085%

    No Known Activations